JP5850057B2 - Content distribution system, control device, and content distribution method - Google Patents

Description

[Description of related applications]
The present invention is based on the priority claim of Japanese patent application: Japanese Patent Application No. 2011-194562 (filed on September 7, 2011), and the entire content of the application is incorporated herein by reference. Shall.
The present invention relates to a content distribution system, a control device, and a content distribution method, and in particular, contents including moving images, still images, audio, software, applications, etc. are cached in a mobile network, and are used for mobile phones, smartphones, PCs (Personal Computers) The present invention relates to a content distribution system that distributes to a terminal such as a game machine, a control device thereof, and a content distribution method.

  With the progress of higher speed and larger capacity of mobile networks, content distribution for distributing contents to various terminals including mobile terminals is becoming widespread through the mobile network. In the future, mobile networks will be further increased in speed and capacity through Long Term Evolution (LTE) and Evolved Packet Core (EPC) technologies.

  For example, Patent Document 1 describes a technique for reducing access time and preventing network congestion by providing a cache device in a content distribution system.

JP 2003-228534 A

  The entire disclosure of the above patent document is incorporated herein by reference. The following analysis was made by the present inventors.

  There is a prediction that the amount of traffic in the data system will increase several tens of times in the mobile network over the next 2013, and video content will occupy most of it. In addition, the size of video content has become larger and larger due to the high performance of terminal capabilities accompanying the rapid spread of smartphones. Therefore, in the near future, it is expected that high-capacity content with high-definition resolution will be distributed on mobile networks.

  On the other hand, when content on the Internet is distributed over a mobile network, in a conventional content distribution system, content requests from all terminals are transmitted to a distribution server device on the Internet via a packet transfer device. The distribution server device distributes content to all terminals via the packet transfer device.

  However, such a configuration causes the following problems.

  When access from terminals concentrates on popular content, traffic that goes to the distribution server device via the mobile network concentrates. In addition, the network load in an area where there are many accesses may increase locally. In these cases, congestion occurs in the mobile network until the distribution server device is reached. At this time, delay and packet loss occur, and there is a problem that QoE (Quality of Experience) deteriorates, such as the image being frozen on the terminal side, the image quality is degraded, and the sound is interrupted. In addition, this problem becomes more serious as the number of terminals increases and the capacity of contents increases.

  In addition, if the popularity of some content changes rapidly due to the introduction of new content, etc., more intense traffic concentration occurs, avoiding further traffic concentration on the distribution server device and network congestion. There is a problem that it is difficult to do.

  Therefore, when distributing content via a mobile network, it is desired to avoid congestion of the mobile network when access to some content is concentrated. The objective of this invention is providing the content delivery system, control apparatus, and content delivery method which contribute to this request.

The content distribution system according to the first aspect of the present invention is:
A packet transfer device for transferring a plurality of contents distributed from a distribution server device on the Internet;
A plurality of cache servers that are provided or connected to the packet transfer device and temporarily hold at least some of the plurality of contents;
The access frequency for each of the at least some contents is collected from the plurality of cache servers, and the content whose access frequency is equal to or higher than a predetermined threshold is arranged on the plurality of cache servers according to a predetermined arrangement, and the others And a control device that arranges the content in the plurality of cache servers according to the access frequency of each content.

The control device according to the second aspect of the present invention is:
A packet transfer apparatus that transfers a plurality of contents distributed from a distribution server apparatus on the Internet, and a packet transfer apparatus that is provided or connected to the packet transfer apparatus, and temporarily stores at least some contents of the plurality of contents In a content distribution system comprising a plurality of cache servers to be held, a control device that controls the plurality of cache servers,
The access frequency for each of the at least some contents is collected from the plurality of cache servers, and the content whose access frequency is equal to or higher than a predetermined threshold is arranged on the plurality of cache servers according to a predetermined arrangement, and the others Are arranged in the plurality of cache servers according to the access frequency of each content.

The content distribution method according to the third aspect of the present invention is:
A packet transfer apparatus that transfers a plurality of contents distributed from a distribution server apparatus on the Internet, and a packet transfer apparatus that is provided or connected to the packet transfer apparatus, and temporarily stores at least some contents of the plurality of contents In a content distribution system including a plurality of cache servers to be held, a control device that controls the plurality of cache servers includes:
Collecting an access frequency for each of the at least some contents from the plurality of cache servers;
Arranging content having an access frequency equal to or higher than a predetermined threshold with respect to the plurality of cache servers according to a predetermined arrangement;
Placing other contents on the plurality of cache servers in accordance with the access frequency of each content.

  According to the content distribution system, the control device, and the content distribution method according to the present invention, when content is distributed through the mobile network, congestion of the mobile network can be avoided when access to some content is concentrated. It becomes possible.

It is a figure which shows the connection structure of the content delivery system which concerns on 1st Embodiment as an example. It is a block diagram which shows the structure of the control apparatus in the content delivery system which concerns on 1st Embodiment as an example. It is a block diagram which shows the structure of the content arrangement | positioning calculation part in the control apparatus of the content delivery system which concerns on 1st Embodiment as an example. It is a block diagram which shows the structure of the cache server in the content delivery system which concerns on 1st Embodiment as an example. It is a figure which shows the connection structure of the content delivery system which concerns on 2nd Embodiment as an example.

  First, the outline of the present invention will be described. Note that the reference numerals of the drawings attached to this summary are merely examples for facilitating understanding, and are not intended to limit the present invention to the illustrated embodiment.

  Referring to FIG. 1, the content distribution system of the present invention is a packet transfer apparatus (SGSN / GGSN (Serving GPRS Support in FIG. 1)) that transfers a plurality of contents distributed from a distribution server apparatus (120) on the Internet (105). Node / Gateway GPRS Support Node) devices 190_1 to 190_N) and a plurality of cache servers (110_1 to 110_1) that are provided to or connected to the packet transfer device and temporarily hold at least some contents of the plurality of contents. 110_N) and the access frequency for each of at least some of the contents from the plurality of cache servers (110_1 to 110_N), and the content having the access frequency equal to or higher than a predetermined threshold is stored in the plurality of cache servers (110_1 to 110_N). To place according to the prescribed arrangement Together, comprising control devices arranged in a plurality of cache servers (110_1～119_N) in accordance with the other contents of the access frequency of each content and (160), the.

  It is preferable that the control device (160) generates a number of replicas corresponding to the access frequency for each content whose access frequency is less than a predetermined threshold, and arranges it on the plurality of cache servers (110_1 to 110_N). Further, it is preferable that the control device (160) arranges content whose access frequency is less than a predetermined threshold in a cache server having a load of a predetermined threshold or less among the plurality of cache servers (110_1 to 110_N). Furthermore, the control device (160) may arrange content whose access frequency is equal to or higher than a predetermined threshold in all of the plurality of cache servers (110_1 to 110_N).

  The control device (160) selects a cache server that holds the content among the plurality of cache servers (110_1 to 110_N) when requested by the terminal (for example, the portable terminal 170) to distribute the content, Instructs the selected cache server to distribute the content. In addition, when there are a plurality of cache servers (110_1 to 110_N) that hold the content requested from the terminal (170), the control device (160) includes a plurality of cache servers. It is preferable to select a cache server having the smallest load and instruct to distribute the content. Further, when the control device (160) is requested by the terminal (170) to distribute the content, when none of the plurality of cache servers (110_1 to 110_N) holds the content, the control device (160) It is preferable to instruct the cache server selected from the cache servers (110_1 to 110_N) to acquire and distribute the content from the distribution server device (120).

  Referring to FIG. 1, the content distribution system according to the present invention includes two or more cache servers (110_1 to 110_N) that temporarily hold at least part of content distributed from a distribution server device (120) on the Internet. ) To a packet transfer device (for example, SGSN / GGSN device 190_1) of the mobile network (150), and at least one control device (160) for controlling two or more cache servers (110_1 to 110_N), The control device (160) considers the cooperation between the cache servers (110_1 to 110_N), calculates the placement on the cache server using predetermined evaluation criteria, and calculates the placement of the content whose placement has been calculated with respect to the cache server. Instruct the cache, the cache server The cache server (for example, 110_1) reads the requested content in consideration of the cooperation between the cache servers when a request is received from the terminal (for example, the portable terminal 170), and the packet transfer device (for example, 190_1) To the terminal (170).

  In the content distribution system according to the present invention, the control device (160) refers to the access frequency for each of the contents stored in the cache servers (110_1 to 110_N), and the content with a high access frequency is sent to a plurality of cache servers. The content is arranged according to a predetermined arrangement, and other contents are arranged in a plurality of cache servers according to the access frequency. Therefore, according to the content distribution system of the present invention, for example, content with a relatively high access frequency is distributed and arranged in a large number of cache servers, and a part of content with a relatively low access frequency according to the frequency. Can be placed on any cache server. According to such a content distribution system, when content is distributed via a mobile network, it is possible to avoid congestion of the mobile network when access to some content is concentrated.

In the present invention, the following modes are possible.
[Form 1]
This is the same as the content distribution system according to the first aspect.
[Form 2]
The control device may generate a number of copies corresponding to the access frequency for each content whose access frequency is less than the predetermined threshold value, and place the duplicates on the plurality of cache servers.
[Form 3]
The control device may arrange content whose access frequency is less than the predetermined threshold on a cache server having a load of a predetermined threshold or less among the plurality of cache servers.
[Form 4]
The control device may arrange content having an access frequency equal to or higher than the predetermined threshold in all of the plurality of cache servers.
[Form 5]
The control device selects a cache server that holds the content from the plurality of cache servers and distributes the content to the selected cache server when requested by the terminal to distribute the content. You may instruct.
[Form 6]
When there are a plurality of cache servers holding the content requested from the terminal among the plurality of cache servers, the control device selects a cache server having the smallest load among the plurality of cache servers. The content may be instructed to be distributed.
[Form 7]
When the control device requests the terminal to deliver the content, if none of the plurality of cache servers holds the content, the control device selects the cache server selected from the plurality of cache servers. The content may be instructed to be acquired from the distribution server device and distributed.
[Form 8]
The control device, when requested by the terminal to distribute the content, acquires the content from the cache server holding the content among the plurality of cache servers and distributes the content The cache server that does not hold the content may be instructed.
[Form 9]
The packet transfer device is an SGSN device, a GGSN device or an SGSN / GGSN device on a mobile network, or an S-GW (Serving Gateway) device on a mobile LTE (Long Term Evolution) / EPC (Evolved Packet Core) network, P -It may be a GW (Packet data network Gateway) device or an S / P-GW device.
[Mode 10]
The plurality of contents may include at least one of a moving image, a still image, sound, audio, software, an application, and data.
[Form 11]
As in the control device according to the second aspect.
[Form 12]
The control device may generate a number of replicas corresponding to the access frequency for each content whose access frequency is less than the predetermined threshold value and place the replicas on the plurality of cache servers.
[Form 13]
The control device may arrange content whose access frequency is less than the predetermined threshold in a cache server having a load of a predetermined threshold or less among the plurality of cache servers.
[Form 14]
The control device may arrange content having an access frequency equal to or higher than the predetermined threshold in all of the plurality of cache servers.
[Form 15]
The control device, when requested by the terminal to deliver the content, selects a cache server that holds the content among the plurality of cache servers, and delivers the content to the selected cache server You may instruct.
[Form 16]
When there are a plurality of cache servers holding the content requested from the terminal in the plurality of cache servers, the control device selects a cache server having the smallest load among the plurality of cache servers. The content may be instructed to be distributed.
[Form 17]
When the control device is requested by the terminal to deliver the content, and none of the plurality of cache servers holds the content, the control device selects the cache server selected from the plurality of cache servers, The content may be instructed to be acquired from the distribution server and distributed.
[Form 18]
The control device, when requested by the terminal to distribute the content, acquires the content from the cache server that holds the content among the plurality of cache servers, and distributes the content You may instruct the cache server which does not hold | maintain the said content among cache servers.
[Form 19]
The content distribution method according to the third aspect is as described above.
[Form 20]
A packet transfer apparatus that transfers a plurality of contents distributed from a distribution server apparatus on the Internet, and a packet transfer apparatus that is provided or connected to the packet transfer apparatus, and temporarily stores at least some contents of the plurality of contents In a content distribution system including a plurality of cache servers to be held,
A process of collecting access frequencies for each of the at least some contents from the plurality of cache servers;
A process of arranging content having an access frequency equal to or higher than a predetermined threshold with respect to the plurality of cache servers according to a predetermined arrangement;
There is provided a program for causing a computer provided in a control device for controlling the plurality of cache servers to execute processing for arranging other contents on the plurality of cache servers according to the access frequency of each content. The program can be provided as a program product recorded on a non-transient computer-readable recording medium.

  Next, the configuration and operation of the content distribution system according to the embodiment will be described in detail with reference to FIGS. In the following embodiments, as an example, a configuration when content is a moving image will be described. However, the same configuration can be adopted when the content is a still image, audio, voice, software, application, data, or the like.

(Embodiment 1)
The content distribution system according to the first embodiment will be described with reference to the drawings. FIG. 1 is a diagram illustrating a connection configuration of a content distribution system according to the present embodiment as an example. Referring to FIG. 1, the content distribution system includes a distribution server device 120 on the Internet 105, and SGSN / GGSN devices 190_1 to 190_N, cache servers 110_1 to 110_N, a control device 160, an RNC (Radio Network) on the mobile network 150. Controller) devices 195_1 to 195_L, 197_1 to 197_L, and base station devices 180_1 to 180_M, 181_1 to 181_M, 182_1 to 182_M, and 183_1 to 183_M.

  FIG. 1 shows a configuration when a 3G (3rd Generation) mobile packet network is used as a mobile network and an SGSN / GGSN apparatus is used as a packet transfer apparatus. Here, the SGSN / GGSN device means a device in which SGSN (Serving GPRS Support Node) and GGSN (Gateway GPRS Support Node) are co-located (located in the same station).

  In FIG. 1, a distribution server device 120 on the Internet 105 distributes Internet content. In the following description, these contents on the Internet are referred to as OTT (Over The Top) contents. Here, the OTT content is a file storing a compression-encoded bitstream or a compression-encoded bitstream of content including at least one of moving images, still images, Web pages, audio, audio, and the like. Although not described here, the content may be software, an application, data, or the like.

  N (N ≧ 2) SGSN / GGSN devices 190_1 to 190_N are arranged on the mobile network 150. RNC devices 195_1 to 195_L (L ≧ 2) are connected to the SGSN / GGSN device 190_1. Similarly, RNC devices 197_1 to 197_L are connected to the SGSN / GGSN device 190_N. Note that L RNC devices are also connected to the SGSN / GGSN device 190_2, but are not shown in FIG. 1 for the sake of space. Further, M (M ≧ 2) base stations are connected per RNC device. For example, M base station apparatuses 180_1 to 180_M are connected to the RNC apparatus 195_1.

  In FIG. 1, one cache server is connected to the GGSN function unit of each SGSN / GGSN apparatus. For example, the cache server 110_1 is connected to the SGSN / GGSN apparatus 190_1. N (N ≧ 2) cache servers 110_1 to 110_N are connected to the control device 160. Further, the cache servers 110_1 to 110_N are connected to each other in order to cooperate between the cache servers.

  The portable terminal 170 transmits a distribution connection request message describing the URL (Uniform Resource Locator) of the content to be requested. Then, the base station device in which the mobile terminal 170 is located (in the case of FIG. 1, any of the base station devices 181_1 to 181_M) receives the connection request message, and manages the RNC device (which manages the base station device). In the case of FIG. 1, a connection request message is sent to the RNC device 195_L).

  The RNC device 195_L receives the connection request message from the base station device, and displays the connection request message, the IP (Internet Protocol) address of the distribution server device 120, the IP address of the portable terminal 170, etc. in the payload portion of the GTP (GPRS Tunneling Protocol) packet. The GTP packet is transferred to the SGSN / GGSN device 190_1 that stores the RNC devices 195_1 to 195_L.

  Next, the SGSN / GGSN apparatus 190_1 receives the GTP packet.

  The cache server 110_1 is connected to the Gi interface of the GGSN function unit of the SGSN / GGSN apparatus 190_1. Similarly, the cache server 110_N is connected to the Gi interface of the GGSN function unit of the SGSN / GGSN apparatus 190_N.

  Cache servers 110_1 to 110_N are connected to the control device 160. The control device 160 causes the content whose access frequency is higher than the threshold Th1 to be placed in a predetermined arrangement on two or more cache servers. On the other hand, the control device 160 calculates an optimal arrangement to the cache servers 110_1 to 110_N for a part or all of the content whose access frequency is less than Th1, and based on the calculation result, the control device 160 Issue content placement instructions.

  When each cache server receives the content placement instruction from the control device 160, the cache server accesses the instructed content on the distribution server device 120 via the SGSN / GGSN device, and accumulates the content in the cache server. In addition, each cache server distributes the requested content to the mobile terminal 170 when requested from the mobile terminal 170.

  Next, the configuration of the control device 160 will be described with reference to the drawings. FIG. 2 is a block diagram illustrating the configuration of the control device 160 as an example. Referring to FIG. 2, the control device 160 includes a control signal transmission / reception unit 161, an access measurement unit 184, a content arrangement calculation unit 185, a cache server selection unit 187, and a content map creation / storage unit 167.

  The control signal transmission / reception unit 161 inputs access frequency information of each content and load information of each cache server from each of the cache servers 110_1 to 110_N. The control signal transmission / reception unit 161 outputs access frequency information to the access measurement unit 184 and outputs additional information to the content arrangement calculation unit 185 and the cache server selection unit 187.

  The access measuring unit 184 collects access frequency information for each content from each cache server every predetermined time or when a predetermined condition is satisfied. The access measuring unit 184 adds and sorts them by the number of cache servers, and totals the access frequency over the entire cache server for each content. Further, the access measurement unit 184 outputs the access frequency for each content to the content arrangement calculation unit 185.

  The content arrangement calculation unit 185 receives the load information of each cache server from the control signal transmission / reception unit 161 and the access frequency for each content from the access measurement unit 184.

  The configuration of the content arrangement calculation unit 185 will be described with reference to the drawings. FIG. 3 is a block diagram illustrating the configuration of the content arrangement calculation unit 185 as an example. Referring to FIG. 3, the content arrangement calculation unit 185 includes a threshold calculation unit 204, a determination unit 201, an arrangement instruction unit 203, and a calculation unit 202.

  The threshold value calculation unit 204 inputs the access frequency of each content from the access measurement unit 184 at predetermined time intervals or at the timing when a request is made, and obtains a threshold value Th1 for the access frequency. For example, the threshold value calculation unit 204 may calculate the average access frequency and access distribution of the entire content, and set a threshold value for the upper Y%. The threshold calculation unit 204 outputs the threshold Th1 to the determination unit 201.

  The determination unit 201 inputs the access frequency of each content from the access measurement unit 184 at every predetermined time or every timing when a request is generated, and inputs the threshold Th1 from the threshold calculation unit 204. The discriminating unit 201 discriminates contents whose access frequency exceeds the threshold Th1 and outputs information on these contents to the arrangement instruction unit 203.

  The placement instruction unit 203 instructs a predetermined placement for content that exceeds the threshold Th1. As the predetermined arrangement, the arrangement instruction unit 203 may instruct the contents whose access frequency exceeds a predetermined threshold Th1 to be arranged in all the cache servers 110_1 to 110_N. The arrangement method is not limited to such a method.

  Further, the determination unit 201 outputs information on content whose access frequency is less than a predetermined threshold Th1 and access frequency information for each of these contents to the calculation unit 202.

  The calculation unit 202 inputs information on content whose access frequency is less than a predetermined threshold Th1 from the determination unit 201 and access frequency information for each of the content, and loads load information on each cache server from the control signal transmission / reception unit 161. input. For example, the calculation unit 202 determines the cache server that stores each content in consideration of the cooperation between the cache servers as follows.

  The calculation unit 202 sorts the contents in descending order of access frequency, and creates Kj copies for each content in order from the content having the highest access frequency. Here, the range of Kj is 0 ≦ Kj ≦ M. Here, j indicates a content number. M is an integer satisfying 0 <M ≦ N. Furthermore, N is the number of cache servers.

  The calculation unit 202 may change the value of Kj from a larger value to a smaller value in descending order of content access frequency. For example, the calculation unit 202 may set Kj to M for content having a high access frequency, and may decrease M-1, M-2,... Every time the access frequency decreases. Further, the calculation unit 202 may set Kj = 1 for content with a low access frequency, and may set Kj = 0 when the cache capacity is exceeded.

  The calculation unit 202 preferably places one copy of the Kj contents on each of the Kj cache servers. Moreover, it is preferable that the calculation part 202 selects a cache server in order with the high access frequency with respect to the said content in each cache server as Kj cache servers. The calculation unit 202 may select Kj cache servers at random.

  When determining the arrangement of content, the calculation unit 202 calculates the total size of the content stored in each cache server using the formula (1), and if the total size exceeds the capacity of the cache server, the calculation unit 202 does not arrange any more. To.

Si = ΣSik (1)
k

  In Expression (1), Si represents the total size (unit: bytes) of the i-th cache server, and Sik represents the size (unit: bytes) of the k-th content arranged in the i-th cache server.

  In order to reduce the amount of processing for determining the content arrangement by the calculation unit 202, the following configuration may be employed. First, the calculation unit 202 may use only a plurality of predetermined cache servers as targets for arranging content. Second, the calculation unit 202 may set only the cache server that satisfies a predetermined condition as a target for arranging content. Here, as the predetermined condition, for example, a condition in which the load information input from each cache server is limited to cache servers having a predetermined threshold value or less can be used. Thirdly, the calculation unit 202 may extract only a predetermined number P of contents less than the threshold Th1 from those having a high access frequency, and set them as targets for arrangement calculation.

  The placement instruction unit 203 receives an output from the calculation unit 202, and instructs each cache server to be placed by the calculation unit 202 to secure and store a copy of the placement target content. The data is transmitted via the transmission / reception unit 161.

  The arrangement instruction unit 203 may instruct the distribution server apparatus 120 to secure a copy of the content to be arranged. As another configuration, when the neighboring cache server other than itself caches the content, the arrangement instructing unit 203 may instruct the cache server to secure a copy of the content. In this case, information indicating which cache server caches the content is read from the content map creation / accumulation unit 167 in FIG. 2 and input to the arrangement instruction unit 203 in FIG.

  Furthermore, the arrangement instructing unit 203 may instruct the cache server to perform the next process for content that is not subject to the arrangement calculation by the calculating unit 202. That is, the arrangement instructing unit 203, when requested by the mobile terminal 170, reads out the corresponding content from the distribution server device 120, caches it in the temporary storage unit 113 of the cache server, and distributes it to the mobile terminal 170 You may instruct. As another configuration, the arrangement instructing unit 203, when requested by the mobile terminal 170, reads out the corresponding content from the distribution server device 120 and does not cache it in the temporary storage unit 113 of the cache server, 170 may be instructed to deliver.

  Returning to FIG. 2, the control device 160 will be described. The cache server selection unit 187 receives content information (for example, URL of content) requested by the mobile terminal 170 from the control signal transmission / reception unit 161 and inputs a content map from the content map creation / storage unit 167. Here, the content map is a map indicating which content is cached by each cache server. The cache server selection unit 187 selects a cache server according to the following procedure. As a first procedure, the cache server calculator unit 187 selects a cache server group that caches the content requested by the mobile terminal 170, and selects an appropriate cache server from the cache server group.

  As another configuration, the following procedure may be added in addition to the first procedure. That is, as the second procedure, the cache server selection unit 187 uses the load information of the cache server for the cache server group selected in the first procedure, and the load is equal to or less than a predetermined threshold. The smallest cache server is selected.

  Next, the cache server selection unit 187 instructs the cache server selected according to the above procedure via the control signal transmission / reception unit 161 to distribute the content requested by the mobile terminal 170. In the content map of the content map creation / accumulation unit 167, when no cache server caches the content, such as content with very low access frequency, the cache server selection unit 187 An instruction to secure content is issued from the device 120.

  The content map creation / accumulation unit 167 receives a content list from each of the cache servers 110_1 to 110_N via the control signal transmission / reception unit 161 at predetermined time intervals, for example, and which content is temporarily stored in which cache server. Create and store a content map that indicates whether it is stored. The content map creation / accumulation unit 167 outputs the content map to the cache server selection unit 187 at predetermined time intervals or whenever there is a request.

  Next, the configuration of the cache server 110_1 connected to the SGSN / GGSN apparatus 190_1 will be described with reference to the drawings. FIG. 4 is a block diagram illustrating an example of the configuration of the cache server 110_1. Note that the configuration of the cache servers 110_2 to 110_N other than the cache server 110_1 is the same as the configuration of the cache server 110_1, and thus the description thereof is omitted. Referring to FIG. 4, the cache server 110_1 includes a control signal transmission / reception unit 111, an analysis unit 115, a content securing unit 112, a content temporary storage unit 113, a content list creation unit 116, an access frequency counting unit 130, a load status detection unit 135, And the delivery part 114 is provided.

  The control signal transmission / reception unit 111 receives the connection request message from the mobile terminal 170 and the GTP packet storing the received IP address of the mobile terminal 170, the URL of the requested content, and the like from the SGSN / GGSN device 190_1.

  The analysis unit 115 reads the content of the connection request message stored in the payload portion of the GTP packet, extracts information such as the received IP address of the mobile terminal 170 and the URL of the requested content, and transmits / receives the information to / from the control signal The data is sent to the control device 160 via the unit 111. The analysis unit 115 also outputs information such as the URL of the content to the access frequency counting unit 130.

  The content securing unit 112 inputs the content placement instruction sent from the placement instruction unit 203 shown in FIG. 3 via the control signal transmission / reception unit 111, and receives the cache server selection instruction sent from the cache server selection unit 187 as a control signal. The content that is input via the transmission / reception unit 111 and instructed to be arranged is secured. Here, in the case of an instruction to secure the content requested from the distribution server device 120 or other cache server, the content securing unit 112 receives the instructed content from the distribution server device 120 or another cache server other than itself. Read and output to the content temporary storage unit 113.

  The content temporary storage unit 113 temporarily caches the content secured and output by the content securing unit 112.

  The content list creation unit 116 sets the content for every content that the cache server 110_1 caches in the content temporary storage unit 113 at predetermined time intervals or when a predetermined condition is satisfied. A list is created, and the content list of the cache server 110_1 is sent to the control device 160 via the control signal transmission / reception unit 111.

  The access count totaling unit 130 inputs the URL information of the requested content from the analysis unit 115 for each content requested to connect to the cache server 110_1. The access frequency counting unit 130 calculates the access frequency for each content by adding the number of connection requests from the portable terminal 170 within a predetermined time range based on the input information. The access frequency calculation unit 130 sends the access frequency for each content to the control device 160 via the control signal transmission / reception unit 111.

  The load status detection unit 135 measures the load status Q of the cache server 110_1 every predetermined time or when a predetermined condition is satisfied, and the measured load status Q is transmitted to the control signal transmission / reception unit 111. To the control device 160. For example, the load status detection unit 135 may be a case where a load status transmission request is sent from the control device 160 to the cache server 110_1. The load condition detection unit 135 may employ other conditions.

  The load situation detection unit 135 calculates the load situation Q according to the equation (2).

Q = ΣAj * Sj (2)
j

  In Expression (2), Q is an index indicating the load status of the cache server 110_1, j is the number of content temporarily stored in the cache server 110_1, Aj is the number of requests for the jth content, and Sj is the size of the jth content. Show. Note that the load state detection unit 135 may calculate the load state using an expression other than Expression (2).

  The distribution unit 114 receives the URL information of the content requested from the analysis unit 115, searches the content temporary storage unit 113 based on the URL information, reads the corresponding content, and then transmits a packet of a predetermined protocol. Is generated. Also, the distribution unit 114 sends the generated packet to the SGSN / GGSN apparatus 190_1 and distributes it to the mobile terminal 170 via the SGSN / GGSN apparatus 190_1. Here, for example, a TCP protocol (Transmission Control Protocol) or an HTTP protocol (Hypertext Transfer Protocol) can be used as a predetermined protocol.

  On the other hand, when the content temporary storage unit 113 does not cache the requested content, when the cache server selection unit 187 in FIG. 2 instructs the distribution server device 120 to read and distribute the content, the distribution unit 11 Reads out the corresponding content from the distribution server device 120, caches it in the content temporary storage unit 113 of the cache server 110_1, generates a packet of a predetermined protocol, and distributes it to the mobile terminal 170. As another configuration, the distribution unit 114 may read the corresponding content from the distribution server device 120, but may distribute the content to the mobile terminal 170 without caching in the content temporary storage unit 113 of the cache server 110_1.

  On the other hand, when the requested content is not cached by the temporary content storage unit 113, the content is read from the cache server selection unit 187 in FIG. In such a case, the distribution unit 114 reads the requested content from the instructed cache server, caches it in the content temporary storage unit 113 of the cache server 110_1, and then transmits a packet of a predetermined protocol. It is generated and distributed to the mobile terminal 170.

  Various modifications can be made to the content distribution system according to the first embodiment described above.

  FIG. 1 shows a configuration when a cache server is connected to a GGSN function unit of SGSN / GGSN. On the other hand, the cache server may be connected to the SGSN function unit. In addition, at least one of the cache server and the control device 160 may be incorporated in the SGSN / GGSN device, or may coexist with the SGSN / GGSN device.

  The number of control devices 160 is not limited to one. Two or more control devices may be provided, and processing may be shared among these control devices. Further, the control device 160 may be incorporated in at least one cache server.

  The threshold value Th1 in the control device 160 may be a predetermined value. Further, the threshold value may be Th1 = 0 or Th1 = ∞. When Th1 = ∞, the access frequency does not exceed Th1, and therefore the content arrangement calculation unit 185 does not arrange the content according to a predetermined arrangement. Note that the control device 160 may not use the load information of each cache server.

  The content arrangement calculation unit 185 may execute the calculation of the content arrangement and the instruction to cache the target content to the target cache server every predetermined time, or may be predetermined. You may implement when conditions are satisfy | filled. Here, as the predetermined condition, for example, when the access frequency of the content aggregated by the access measuring unit 184 is changed compared to the past access frequency, and the degree of change exceeds a predetermined threshold value It is possible to use a condition that it is implemented. However, the content arrangement calculation unit 185 can use other conditions. The content arrangement calculation unit 185 may calculate the arrangement of content based on another configuration.

  The load situation detection unit 135 may calculate the load situation using an expression other than the expression (2).

  Further, in FIG. 1, the cache servers 110_1 to 110_N are connected to each other so that the cache servers are linked to exchange contents. However, the cache servers 110_1 to 110_N may operate independently without being connected to each other.

  FIG. 1 shows a configuration in which one cache server is connected to one SGSN / GGSN apparatus. However, one cache server may be connected to a plurality of SGSN / GGSN devices. A plurality of cache servers may be connected to one SGSN / GGSN device.

  Further, the distribution server device 120 may be connected to the cache server devices 110_1 to 110_N.

  Furthermore, FIG. 1 shows a configuration in the case of using an SGSN / GGSN device in which an SGSN device and a GGSN device are integrated. However, the structure which isolate | separated the SGSN apparatus and the GGSN apparatus can also be used. In this case, at least one cache server is connected to either the SGSN device or the GGSN device.

  In addition, the mobile terminal 170 may be any of a mobile phone, a smartphone, and a PC in which a data communication card is mounted. The mobile terminal 170 may be any other terminal as long as it can communicate with the mobile 3G network.

(Embodiment 2)
A content distribution system according to a second embodiment will be described with reference to the drawings. FIG. 5 is a diagram illustrating an example of the configuration of the content distribution system according to the present embodiment.

  In FIG. 5, the constituent elements having the same numbers as those in FIG. 1 perform the same operations as those in FIG. FIG. 5 shows a configuration in which an LTE (Long Term Evolution) / EPC (Evolved Packet Core) network, which is a 3.9 generation mobile network, is used as the mobile network 250 instead of the 3G mobile network. In LTE, the functions of the base station device and the RNC device are degraded, and only the eNodeB device is provided.

  In EPC, an S / P-GW (Serving / Packet Data-Gateway) device is connected to the eNodeB device. Here, the S / P-GW device means that the S-GW device and the P-GW device are integrated. FIG. 5 shows a configuration in which M eNodeB devices are connected to one S / P-GW device. For example, eNodeB devices 260_1 to 260_M are connected to the S / P-GW device 290_1.

  Here, one cache server is connected to each S / P-GW apparatus. For example, the cache server 110_1 is connected to the S / P-GW apparatus 290_1.

  The portable terminal 170 describes the IP address of the distribution server device 120 and issues a distribution connection request message. Then, the eNodeB device in which the mobile terminal 170 is located (in the case of FIG. 5, one of the eNodeB devices 261_1 to 261_M) receives the connection request message. Any of the eNodeB devices 261_1 to 261M stores the connection request message, the IP address of the distribution server device 120, the IP address of the mobile terminal 170, etc. in the payload portion of the GTP protocol, and sends the GTP packet to the S / P-GW device 290_2. Forward.

  The cache server 110_1 has the same configuration as that shown in the cache server 110_1 (FIG. 4) in the first embodiment. However, in this embodiment, the connection destination of the control signal transmission / reception unit 111 is the S / P-GW apparatus 290_1. Therefore, the control signal transmission / reception unit 111 receives the connection request message from the portable terminal 170, the GTP packet storing the IP address, and the location information of the portable terminal 170 from the S / P-GW apparatus 290_1. The other cache servers 110_2 to 110_N also perform the above exchanges with the S / P-GW apparatuses 290_2 to 290_N connected thereto.

  In the present embodiment, the distribution server device 120 is connected to the S / P-GW devices 290_1 to 290_N.

  Various modifications can be made to the content distribution system according to the second embodiment described above. However, since the modification is the same as the modification described in the first embodiment, detailed description thereof is omitted.

  FIG. 5 shows a configuration in which one cache server is connected to one S / P-GW apparatus. However, one cache server may be connected to a plurality of S / P-GW apparatuses. A plurality of cache servers may be connected to one S / P-GW device.

  FIG. 5 shows a configuration using an S / P-GW apparatus in which an S-GW apparatus and a P-GW apparatus are integrated. However, the structure which isolate | separated the S-GW apparatus and the P-GW apparatus is also employable. In this case, at least one cache server is connected to either the S-GW apparatus or the P-GW apparatus.

  According to the content distribution system according to the first and second embodiments, for example, the following effects are brought about.

  The control device 160 causes a predetermined arrangement to two or more cache servers for content whose access frequency is higher than the threshold. In addition, for a part of content whose access frequency is less than the threshold, the control device 160 calculates the placement on the cache server for each content using the access frequency information or the like. Further, the control device 160 instructs the cache server to cache the content determined to be arranged, and the cache server temporarily caches and distributes the content.

  At this time, it becomes possible to avoid the concentration of the load on the mobile network and the concentration of the access to the distribution server device 120 with respect to the popular content, and the congestion of the mobile network can be avoided. In addition, this effect becomes significant when the number of terminals increases or when the contents increase in capacity. From the user's point of view, there is no delay or packet loss, and there is an effect that the image is not frozen on the terminal side or the sound is interrupted.

  Furthermore, even if the popularity changes rapidly due to the introduction of new contents, etc., there is an effect that it is possible to avoid congestion by avoiding traffic concentration on the distribution server device and the network.

  Furthermore, according to such a content distribution system, the above-described effects can be brought about without modifying the terminal at all.

  It should be noted that the disclosures of prior art documents such as the above patent documents are incorporated herein by reference. Within the scope of the entire disclosure (including claims) of the present invention, the embodiment can be changed and adjusted based on the basic technical concept. Various disclosed elements (including each element of each claim, each element of each embodiment, each element of each drawing, etc.) can be combined or selected within the scope of the claims of the present invention. . That is, the present invention of course includes various variations and modifications that could be made by those skilled in the art according to the entire disclosure including the claims and the technical idea. In particular, with respect to the numerical ranges described in this document, any numerical value or small range included in the range should be construed as being specifically described even if there is no specific description.

105 Internet 110_1 to 110_N Cache server 111 Control signal transmission / reception unit 112 Content securing unit 113 Content temporary storage unit 114 Distribution unit 115 Analysis unit 116 Content list creation unit 120 Distribution server device 130 Access frequency counting unit 135 Load status detection unit 150 Mobile network 160 Control device 161 Control signal transmission / reception unit 167 Content map creation / storage unit 170 Portable terminals 180_1 to 180_M, 181_1 to 181_M, 182_1 to 182_M, 183_1 to 183_M Base station device 184 Access measurement unit 185 Content allocation calculation unit 187 Cache server selection unit 190_1 ~ 190_N SGSN / GGSN apparatus 195_1 to 195_L, 197_1 to 197_L RNC apparatus 201 discrimination unit 202 Calculation unit 203 arrangement instructing section 204 threshold value calculation unit 250 mobile LTE / EPC network 260_1~260_M, 261_1~261_M, 262_1~262_M eNodeB device 290_1~290_N S / P-GW device Th1 threshold

Claims (19)

A packet transfer device for transferring a plurality of contents distributed from a distribution server device on the Internet;
A plurality of cache servers that are provided or connected to the packet transfer device and temporarily hold at least some of the plurality of contents;
The access frequency for each of the at least some contents is collected from the plurality of cache servers, and the content whose access frequency is equal to or higher than a predetermined threshold is arranged on the plurality of cache servers according to a predetermined arrangement, and the others A content distribution system comprising: a control device that arranges the content in the plurality of cache servers according to the access frequency of each content.   The content distribution according to claim 1, wherein the control device generates a number of replicas corresponding to the access frequency for each content having an access frequency less than the predetermined threshold, and places the duplicates on the plurality of cache servers. system.   3. The content distribution system according to claim 1, wherein the control device arranges content whose access frequency is less than the predetermined threshold in a cache server having a load equal to or lower than the predetermined threshold among the plurality of cache servers. . 4. The content placement system according to claim 1, wherein the control device places a copy of the content having an access frequency equal to or higher than the predetermined threshold on all of the plurality of cache servers. 5.   The control device selects a cache server that holds the content from the plurality of cache servers and distributes the content to the selected cache server when requested by the terminal to distribute the content. The content distribution system according to any one of claims 1 to 4, wherein instructions are given as follows.   When there are a plurality of cache servers holding the content requested by the terminal in the plurality of cache servers, the control device selects a cache server having the smallest load among the plurality of cache servers. The content distribution system according to claim 5.   When the control device requests the terminal to deliver the content, if none of the plurality of cache servers holds the content, the control device selects the cache server selected from the plurality of cache servers. The content distribution system according to claim 1, wherein the content distribution system instructs to acquire and distribute the content from the distribution server device.   The control device, when requested by the terminal to distribute the content, acquires the content from the cache server holding the content among the plurality of cache servers and distributes the content The content distribution system according to any one of claims 1 to 7, wherein an instruction is given to a cache server that does not hold the content among the cache servers.   The packet transfer device is an SGSN (Serving GPRS Support Node) device, a GGSN (Gateway GPRS Support Node) device or an SGSN / GGSN device on a mobile network, or a mobile LTE (Long Term Evolution) / EPC (Evolved Packet Core) network. The content distribution system according to any one of claims 1 to 7, which is the above S-GW device, P-GW device, or S / P-GW device.   The content distribution system according to any one of claims 1 to 9, wherein the plurality of contents include at least one of a moving image, a still image, sound, audio, software, an application, and data. A packet transfer apparatus that transfers a plurality of contents distributed from a distribution server apparatus on the Internet, and a packet transfer apparatus that is provided or connected to the packet transfer apparatus, and temporarily stores at least some contents of the plurality of contents In a content distribution system comprising a plurality of cache servers to be held, a control device that controls the plurality of cache servers,
The access frequency for each of the at least some contents is collected from the plurality of cache servers, and the content whose access frequency is equal to or higher than a predetermined threshold is arranged on the plurality of cache servers according to a predetermined arrangement, and the others The control device arranges the content of the content in the plurality of cache servers according to the access frequency of each content.   The control device according to claim 11, wherein for each content whose access frequency is less than the predetermined threshold, a number of copies corresponding to the access frequency is generated and arranged in the plurality of cache servers.   The control device according to claim 11 or 12, wherein content whose access frequency is less than the predetermined threshold is arranged in a cache server having a load of a predetermined threshold or less among the plurality of cache servers. The control device according to any one of claims 11 to 13, wherein a copy of content having an access frequency equal to or higher than the predetermined threshold is arranged in all of the plurality of cache servers.   When a terminal requests distribution of content, the cache server that holds the content is selected from the plurality of cache servers, and the selected cache server is instructed to distribute the content. The control device according to any one of claims 11 to 14.   When there are a plurality of cache servers holding the content requested from the terminal among the plurality of cache servers, the cache server having the smallest load among the plurality of cache servers is selected and the content is selected. The control device according to claim 15, wherein the control device instructs delivery.   When none of the plurality of cache servers holds the content when requested by the terminal to deliver the content, the content is sent to the cache server selected from the plurality of cache servers. The control device according to claim 11, wherein the control device instructs to acquire and distribute from a distribution server.   Among the plurality of cache servers, when the terminal requests to distribute the contents, the contents are acquired from the cache server holding the contents among the plurality of cache servers and distributed. The control device according to claim 11, wherein the control device instructs a cache server that does not hold the content. A packet transfer apparatus that transfers a plurality of contents distributed from a distribution server apparatus on the Internet, and a packet transfer apparatus that is provided or connected to the packet transfer apparatus, and temporarily stores at least some contents of the plurality of contents In a content distribution system including a plurality of cache servers to be held, a control device that controls the plurality of cache servers includes:
Collecting an access frequency for each of the at least some contents from the plurality of cache servers;
Arranging content having an access frequency equal to or higher than a predetermined threshold with respect to the plurality of cache servers according to a predetermined arrangement;
Placing other contents on the plurality of cache servers according to the access frequency of each content.

Images